Abstract

The previous fine-grained datasets mainly focus on classification and are often captured in a controlled setup, with the camera focusing on the objects. We introduce the first Fine-Grained Vehicle Detection (FGVD) dataset in the wild, captured from a moving camera mounted on a car. It contains 5502 scene images with 210 unique fine-grained labels of multiple vehicle types organized in a three-level hierarchy. While previous classification datasets also include makes for different kinds of cars, the FGVD dataset introduces new class labels for categorizing two-wheelers, autorickshaws, and trucks. The FGVD dataset is challenging as it has vehicles in complex traffic scenarios with intra-class and inter-class variations in types, scale, pose, occlusion, and lighting conditions. The current object detectors like yolov5 and faster RCNN perform poorly on our dataset due to a lack of hierarchical modeling. Along with providing baseline results for existing object detectors on FGVD Dataset, we also present the results of a combination of an existing detector and the recent Hierarchical Residual Network (HRN) classifier for the FGVD task. Finally, we show that FGVD vehicle images are the most challenging to classify among the fine-grained datasets.

Abstract

Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) are neurogenerative impairments with similar symptoms and risk factors. Sulcal width and depth are known biomarkers for discriminating between AD and MCI. This paper presents a novel 2D image representation for a brain mesh surface, called a height map. The basic idea behind the height map is to represent the surface as a function of spherical coordinates of the mesh vertices. We present a method to derive a height map from a given neuroimage (MRI) and extract sulcal regions from the height map. We demonstrate the height map’s utility for classifying a given neuroimage into healthy, MCI and AD classes. Two approaches for extracting sulcal regions are explored. The proposed method is computationally light, and obtaining sulcal regions from a brain surface mesh takes about 24 seconds on a standard Intel i5-7200 CPU. The proposed method achieves 76.1% accuracy, and 76.3% F1-score for healthy, MCI, AD classification on a publicly available dataset.

Abstract

Normative aging trends of the brain can serve as an important reference in the assessment of neurological structural disorders. Such models are typically developed from longitudinal brain image data—follow-up data of the same subject over diferent time points. In practice, obtaining such longitudinal data is difcult. We propose a method to develop an aging model for a given population, in the absence of longitudinal data, by using images from diferent subjects at diferent time points, the so-called cross-sectional data. We defne an aging model as a difeomorphic deformation on a structural template derived from the data and propose a method that develops topology preserving aging model close to natural aging. The proposed model is successfully validated on two public crosssectional datasets which provide templates constructed from diferent sets of subjects at diferent age points.

Abstract

We present PanoHDR-NeRF, a neural representation of the full HDR radiance field of an indoor scene, and a pipeline to capture it casually, without elaborate setups or complex capture protocols. First, a user captures a low dynamic range (LDR) omnidirectional video of the scene by freely waving an off-the-shelf camera around the scene. Then, an LDR2HDR network uplifts the captured LDR frames to HDR, which are used to train a tailored NeRF++ model. The resulting PanoHDR-NeRF can render full HDR images from any location of the scene. Through experiments on a novel test dataset of real scenes with the ground truth HDR radiance captured at locations not seen during training, we show that PanoHDR-NeRF predicts plausible HDR radiance from any scene point. We also show that the predicted radiance can synthesize correct lighting effects, enabling the augmentation of indoor scenes with synthetic objects that are lit correctly. Datasets and code are available at https://lvsn.github.io/PanoHDR-NeRF/.

Abstract

Biometric noise is often discarded in many biometric template protection systems. However, the noise ratio be- tween two templates encodes specific correlational proper- ties that template protection schemes can exploit. Biometric authentication usually occurs between mutually distrusting parties, which calls for privacy-preserving techniques. In this paper, we propose a novel biometric authentication pro- tocol, SIAN(Secure Iris Authentication using Noise), adapt- ing secure two-party computation and incorporating un- certainty constraints from biometric noise for security. We evaluate it on three iris datasets: MMU v1, Ubiris v1, and IITD v1, and observe a low EER degradation. The pro- posed protocol has information-theoretic security and low computational complexity, making it suitable for practical real-time applications.

Abstract

Active Learning aims to solve the problem of alleviating labelling costs for large-scale datasets by selecting a subset of data to effectively train on. Deep Active Learning (DAL) techniques typically involve repeated training of a model for sample acquisition over the entire subset of labelled data available in each round. This can be prohibitively expensive to run in real-world scenarios with large and constantly growing data. Some work has been done to address this – notably, SelectionVia-Proxy (SVP) proposed the use of a separate, smaller “proxy” model for acquisition. We explore further optimizations to the standard DAL setup and propose CLActive: an optimization procedure that brings significant speedups which maintains a constant training time for the selection model across rounds and retains information from past rounds using Experience Replay. We demonstrate large improvements in total train-time compared to the fully-trained baselines and SVP. We achieve up to 89×, 7×, 61× speedups over the fully-trained baseline at 50% of dataset collection in CIFAR, Imagenet and Amazon Review datasets, respectively, with little accuracy loss. We also show that CLActive is robust against catastrophic forgetting in a challenging class-incremental active-learning setting. Overall, we believe that CLActive can effectively enable rapid prototyping and deployment of deep AL algorithms in real-world use cases across a variety of settings.

Abstract

Kathakali is one of the major forms of Classical Indian Dance. The dance form is distinguished by the elaborately colourful makeup, costumes and face masks. In this work, we present (a) a framework to analyze the facial expressions of the actors and (b) novel visualization techniques for the same. Due to extensive makeup, costumes and masks, the general face analysis techniques fail on Kathakali videos. We present a dataset with manually annotated Kathakali sequences for four downstream tasks, i.e. face detection, background subtraction, landmark detection and face segmentation. We rely on transfer learning and fine-tune deep learning models and present qualitative and quantitative results for these tasks. Finally, we present a novel application of style-transfer of Kathakali video onto a cartoonized face. The comprehensive framework presented in the paper paves the way for better understanding, analysis, pedagogy and visualization of Kathakali videos.

Abstract

The simulation of appropriate ground motion is the main objective in earthquake-resistant designing to mitigate the impact of landslides and structural damages. The seismic hazard studies serve as the basis for quantifying the hazard associated within the particular area over a given time period. In this study, the detailed site specific hazard analysis of Tindharia site as well as Darjeeling Sikkim Himalaya (DSH) region has been carried out to assure the safety of human and infrastructure against seismic risk. The study area is mountainous region on north western side of India, falls in seismic zone IV and V, and is one of the most seismically active regions with vulnerable earthquakes along with fatal landslides. The future large earthquakes are likely to occur in the region due to constant movement of Indian plate towards Eurasian plate.Therefore, the heightened seismic risk increases the demand for seismic studies near the Himalayan belt. Thus, the assessment of associated seismic hazard in the study area has been carried out by deterministic and probabilistic seismic hazard approaches. From the results, the seismo-tectonic map of a 300km radial distance of the study area is developed. The deterministic hazard distribution in terms of peak ground acceleration (PGA) and the PGA and peak spectral acceleration (PSA) hazard maps for 2% and 10% probability of exceedance in 50 years at different time periods have been generated. The updated hazard maps developed in this study play pivotal roles in mitigation measures with better pre-disaster prevention by earthquake resistant design and in preparedness and post disaster rescue in the study area

Abstract

The present study compared various empirical and data-driven algorithms to predict Actual Evapotranspiration (AET) using various hydro climatic variables. The AET over semi-arid climatic conditions of Hyderabad, Telangana, India, and Waipara (New Zealand) was estimated using different empirical methods-based PET using Budyko and Turc models. Modelled PET from five data-driven algorithms, such as Long short-term memory neural networks (LSTM), Artificial Neural Network (ANN), Gradient Boosting Regressor, Random Forest, and Support Vector Regression were trained to predict AET using meteorological variables. The results show simple empirical-based AET models, Budyko and Turc, can estimate AET very well. The results indicated that 99% accuracy could be achieved with all climatic input, whereas accuracy drops to 86% with limited data. Both LSTM and ANN models based on PET have been noted as the most robust models for estimating AET with minimal climate data. It was observed that the meteorological variables of temperature and solar radiation have more significant contributions than other variables in the estimation of AET. In addition, the effects of the meteorological variables were found to be essential and effective in the estimation of AET. The research findings of the study reveal that under limited data availability, the best input combinations were identified as temperature and wind speed for estimating PET; temperature, wind speed, and precipitation for estimating AET for semi-arid climatology.

Abstract

Clause recommendation is the problem of recommending a clause to a legal contract, given the context of the contract in question and the clause type to which the clause should belong. With not much prior work being done toward the generation of legal contracts, this problem was proposed as a first step toward the bigger problem of contract generation. As an open-ended text generation prob-lem, the distinguishing characteristics of this problem lie in the nature of legal lan-guage as a sublanguage and the considerable similarity of textual content within the clauses of a specific type. This similarity aspect in legal clauses drives us to investi-gate the importance of similar contracts’ representation for recommending clauses. In our work, we experiment with generating clauses for 15 commonly occurring clause types in contracts expanding upon the previous work on this problem and analyzing clause recommendations in varying settings using information derived from similar contracts.